agentleFS
cwhited26cwhited26/pocket-agent-starter-skills/skills/research/customer-voice-extract/SKILL.md

customer-voice-extract

Skill0 starsChanged 4 months agoMITView on GitHub

Mine a transcript or review for the lines that sound like a real person, not a paraphrase — the exact words you can use in copy. Building marketing copy, case studies, or messaging from a call recording, a review, or a testimonial. Anytime you need the customer's actual voice.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look for emotion and specificity — the lines where they got real, named a number, or described the moment it clicked.

    line 21
  2. Distinctive:

    Keep the rough edges. Real speech has them.

    line 22
  3. Distinctive:

    Never invent or "clean up" a quote into something they didn't say.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pull Real Customer Quotes

The best copy is words a customer already said. Pull the verbatim lines that carry emotion and specificity, not your smoothed-over summary of them — the rough, real phrasing is what other customers recognize.

The technique

  • Pull verbatim. The exact phrase ("I was drowning in paperwork") beats your paraphrase ("the client experienced administrative challenges") every time.
  • Look for emotion and specificity — the lines where they got real, named a number, or described the moment it clicked.
  • Keep the rough edges. Real speech has them; polishing a quote into marketing-speak kills the thing that made it believable.
  • Tag each quote with what it proves — the pain, the result, the objection it overcomes — so you know where to use it.
  • Never invent or "clean up" a quote into something they didn't say. A fabricated testimonial is a liability, not an asset.

Do this, not that

Do: Pull: "Honestly I'd given up on finding someone who'd just show up when they said they would." — it's specific, emotional, and overcomes the no-show objection in the customer's own voice.

Don't: Summarize it into "The customer valued our reliability and professionalism" — true, dead, and indistinguishable from every other company's testimonials.

Why this works

Prospects trust other customers' words far more than the company's. A verbatim quote with its rough edges intact reads as real — someone like them, talking like them. The moment you paraphrase it into clean marketing language, it sounds like you wrote it, and it stops doing the one job a testimonial has: proof from a peer.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.